Mobile manipulation systems have advanced significantly in recent years. However, substantial gaps remain that prevent state-of-the-art platforms from achieving widespread real-world deployment, particularly in reliably grasping items in unstructured environments. To help bridge this gap, we develop SHOPPER, a mobile manipulation robot platform designed to push the boundaries of reliable and generalizable grasp strategies. We develop these grasp strategies and deploy them in a real-world grocery store--an exceptionally challenging setting chosen for its vast diversity of manipulable items, fixtures, and layouts. In this work, we present our detailed approach to designing general grasp strategies towards picking any item in a real grocery store. Additionally, we provide an in-depth analysis of our latest real-world field test, discussing key findings related to fundamental failure modes over hundreds of distinct pick attempts. Through our detailed analysis, we aim to offer valuable practical insights and identify key grasping challenges, which can guide the robotics community towards pressing open problems in the field. Lastly, we provide a dataset of 1200+ grasp attempts in unseen grocery stores.

Robots can be used to mitigate risks in unsafe and austere settings. In recent years, explosive ordnance disposal robots have reduced the technician's time-on-target, and thus, reduce the direct risk of exposure. This article focuses on the study and development of innovative techniques as the foundational work for a new robot platform. The proposed system includes an organic electrochemical transistor device to detect the existence of explosive residues, and lead to decisions for safe-removal progress. Taurus' surgical gripper facilitates object tactile exploration, and manipulation with control precision to the millimeter range. The highly sensitive triboelectric tactile sensor could reduce intrusiveness during contact, and mitigate the risk of detonation. Haptic devices and visual displays are used to convey important signals, in order to improve the situational awareness of the teleoperator. A machine learning classifier can be used to assist the user to identify objects from tactile sampling. The integration of these methodologies allows for a sensitive approach to concealed objects that are only accessible through tactile sensing.

Robotic manipulation of highly deformable materials is inherently challenging due to the need to maintain tension and the high dimensionality of the state of the material. Past work in this area mostly focuses on generating a detailed model for the material and its interaction with the robot, then using the model to construct a motion plan. In this paper, we take a different approach by using only sensor feedback to dictate the robot motion. We consider the collaborative manipulation of a deformable sheet between a person and a dual-armed robot (Baxter by Rethink Robotics). The robot is capable of contact sensing via joint torque sensors and is equipped with a head-mounted RGBd sensor. The robot senses contact force to maintain tension of the sheet, and in turn comply to the human motion. This is akin to handling a tablecloth with a partner but with one's eyes closed. To improve the response, we use the RGBd sensor to detect folds, and command the robot to move in an orthogonal direction to smooth them out. This is like handling cloth by looking at the cloth itself. Both controllers are able to follow human motion without excessive crimps in the sheet, but as expected, the hybrid controller combining force and vision outperforms the force controller alone in terms of tension force transient. The ability to quickly detect the state of the deformable material also enables more complex manipulation strategies in the future.

Input/output transport delay is prevalent in process control, causing performance degradation and even instability. This paper focuses on input and measurement delays in robot force control with stiff environments which tend to be susceptible to modeling error and disturbances. Traditional remedies include increasing the sampling rate, adding passive compliance, or modifying the feedback algorithm, e.g., using integral force feedback instead of proportional feedback. For force control using industrial robots, the problem is even more severe, as the loop closure is done at the outer kinematic loop through setpoint modification, which typically has long actuation latency, in addition to force measurement delay. In this paper, we apply two types of delay compensation to force control for a spring-type environment via direct cancellation: Smith Predictor, and its variant Åström Predictor. We show through simulation, and experimental validation on an industrial robot arm, that both methods significantly improve the stability margin as compared to the typical integral force control, with the Åström Predictor further improving the dynamical response by decoupling delay compensation and tracking response.

We present a novel system to achieve coordinated task-based control on a dual-arm industrial robot for the general tasks of visual servoing and bimanual hybrid motion/force control. The industrial robot, consisting of a rotating torso and two seven degree-of-freedom arms, performs autonomous vision-based target alignment of both arms with the aid of fiducial markers, two-handed grasping and force control, and robust object manipulation in a tele-robotic framework. The operator uses hand motions to command the desired position for the object via Microsoft Kinect while the autonomous force controller maintains a stable grasp. Gestures detected by the Kinect are also used to dictate different operation modes. We demonstrate the effectiveness of our approach using a variety of common objects with different sizes, shapes, weights, and surface compliances.

This paper presents a mobile assistive robot that may be controlled by a mobility disabled user to perform a variety of tasks. Recent research in manipulation-based assistive robotics tends to focus on creating an autonomous robotic assistant. In contrast, our approach allows the user to manually control the robot assistant while providing guidance to the user task execution based on sensor measurements. Our implementation involves the integration of a dual-arm Baxter robot by Rethink Robotics mounted on a power wheelchair commanded by various inputs, including a sip-puff device called the Jamboxx. We call this system the Jamster. The Baxter is lightweight, can operate off the wheelchair battery through an inverter, and is safer to operate around human than traditional industrial robots. A graphical user interface with camera feedback and graphical rendition of the robot enables the user to drive the wheelchair and command the robot to perform simple tasks remotely. As an initial test of this system, we set up a simple task involving driving the Jamster to the shelf to pick up a peanut butter jar and transport it to another location - to be performed with Jamboxx only, without using one's hands. Such task is challenging if not impossible for severely mobility-impaired individuals. This work represents the first step towards our ultimate vision of a robotic assistant that could seamlessly work with mobility disabled individuals to effectively perform daily tasks and thus improve their quality of life.

Ever higher demands on modern mechatronic systems, along with increasing complexity and high development pressure, require a high degree of automation in the model-based development process. An automated generation of topology-oriented models on the basis of requirements, solution patterns, and solution elements poses new challenges to the design and application of state- and parameter estimators for control and condition monitoring. This paper presents a methodology for a highly automated integration of such models into a filter that can be used in real time for state- and parameter estimation as well as the layout of this filter. There need not be any expert knowledge of the underlying model or the algorithms of the filter. The presented methodology and applied tools are able to avoid the drawbacks of established procedures while achieving a considerably higher accuracy in the results.

This paper presents a novel telerobotic framework for human-directed dual-arm manipulation. Current telerobotic systems typically involve a single robot arm commanded by human through a joystick or a master arm. In contrast, our system involves a dual-arm robot manipulating a held object through human gestures without any mechanical coupling. Our experiment involves an industrial robot consisting of a torso, two seven degree-of-freedom arms, and two three-finger hands. We use the existing industrial robot controller, and only modify the position setpoint in the outer loop. The human interfaces to the robot using a set of gesture vocabulary. During object manipulation, the human gesture is interpreted as the desired configuration of the object. The robot performs autonomous vision-based target identification and alignment, grasp selection and force control, to ensure stable and robust object manipulation, with no demand on human for stable grasping. The heterogeneous components of the system are integrated through Robot Raconteur, a distributed communication and control software system. The system interfaces easily to powerful analysis and visualization tools, facilitating rapid algorithm development and prototyping. We envision that the integrated architecture will serve as the foundation for versatile, robust, and safe human-robot collaboration in increasingly complex sensing and manipulation tasks.

Für den Erfolg in Studium und Beruf ist aktuelles und methodisches Wirtschaftswissen das A und O. Die Zeitschrift WiSt liefert dieses Wissen Monat für Monat. Hochaktuelle Wirtschaftsthemen werden vor dem Hintergrund der volks- und betriebswirtschaftlichen Modelle erörtert und diskutiert. So bleiben Sie up-to-date, kennen die brisanten Details und durchschauen schnell komplexe Wirtschaftsstrukturen.

Tracking moving objects is one of the most important but problematic features of motion analysis and understanding. The Kalman filter (KF) has commonly been used for estimation and prediction of the target position in succeeding frames. In this paper, we propose a novel and efficient method of tracking, which performs well even when the target takes a sudden turn during its motion. The proposed method arbitrates between KF and Optical flow (OF) to improve the tracking performance. Our system utilizes a laser to measure the distance to the nearest obstacle and an infrared camera to find the target. The relative data is then fused with the Arbitrate OFKF filter to perform real-time tracking. Experimental results show our suggested approach is very effective and reliable for estimating and tracking moving objects.